Software performance for the automated identification of bird vocalisations: the case of two closely related species

ABSTRACT

Autonomous recording units now facilitate the large collection of audio recordings. However, the analysis of large amounts of acoustic data remains a challenge. The time required for manually searching for bird vocalisations may be equivalent or greater to the duration of audio recordings. This major constraint can be significantly reduced through the use of software developed for automated identification of bird vocalisations in audio recordings. We have compared the performance of four software (CallSeeker, Kaleidoscope Pro, Raven Pro, and Song Scope) and a Convolutional Neural Network (CNN) using audio recordings containing calls of Bicknell’s Thrush and Gray-Cheeked Thrush, as well as the vocalisations of other bird species whose acoustic characteristics overlap with those of our target species. We evaluated all the software on the basis of two main criteria, their ability to detect calls and their ability to classify them correctly by species. Software performance ranged from 30 to 90% in terms of call detection (recall) and from 27 to 99% in terms of correct call classification (precision). CNNs offer a promising solution to the long-standing problem of detecting animal vocalisations in noisy soundscapes, while eliminating the tedious manual step of configuring the algorithms to maximise software performance.

KEYWORDS:

• Bioacoustics
• Software
• Automated identification
• Convolutional neural network
• Noisy soundscapes

Acknowledgements

We are grateful to Birds Canada, the Canadian Wildlife Service-Quebec region of Environment and Climate Change Canada (ECCC), the Macaulay Library and the Vermont Centre for Ecostudies for providing access to their recordings containing the identified calls of the Bicknell’s Thrush and the Gray-cheeked Thrush. We thank ECCC for helping with the labelling of the audio recordings (Stéphanie Gagnon, Céline Maurice). We thank two anonymous reviewers for their helpful and thoughtful comments that improved the manuscript. We also thank Dr. Christopher Scott for reviewing and commenting on this work. All of the authors of this manuscript were involved in the creation of the CallSeeker software. This work was supported by Canadian Wildlife Service-Quebec Region. We are also grateful for the funding received as part of ECCC’s “Innovate with Artificial Intelligence Dragon’s Den” competition, coordinated by the Chief Data Officer and Chief Information Officer.

Author Contributions:

All authors conceived the ideas and designed the methodology, FF and JM analysed the data and led the writing of the manuscript. All authors contributed critically to the drafts and gave final approval for publication.

Disclosure statement

All of the authors of this manuscript were involved in the creation of the CallSeeker software, which is one of the software whose performance we are comparing.

Supplementary materials

Supplemental data for this article can be accessed here.